Study: AI Improves Physicians’ Ability to Assess Extent of Prostate Cancer

 Avenda Health is sharing findings of a new study that demonstrate its artificial intelligence (AI)-powered technology’s potential in improving oncology imaging and cancer diagnostics. 

Titled, “Artificial Intelligence Improves the Ability of Physicians to Identify Prostate Cancer Extent,” the study found AI-assisted cancer identification with Unfold AI—Avenda Health’s AI-powered cancer mapping technology—improved urologists and radiologists abilities in identifying cancer extent by 45x. The study appeared in The Journal of Urology. 

In the study, researchers compared physicians’ performance when they used AI (and did not) to create cancer margins that encompass all clinically significant prostate cancer while minimizing non-malignant tissue within the margin. The multi-reader, multi-case study involved seven urologists and three radiologists from five different institutions and spanning decades of experience, assessing 50 different prostate cancer cases each.

The readers initially defined cancer margins manually, and after a period of at least four weeks, used AI software to define cancer margins. The study found AI-assisted cancer margins significantly outperformed cognitively-defined and hemi-gland margins, with a balanced accuracy of 84.7% compared to 67.2% and 75.9%, respectively. 

Importantly, AI-assisted margins reduced the underestimation of cancer extent, with a negative margin rate of 72.8% compared to 1.6% for cognitively-defined margins. The results show Unfold AI can enhance accuracy in defining prostate cancer margins, leading to improved patient outcomes by informing better treatment strategies. 

The study demonstrates an AI-focused approach has the potential to elevate the efficacy of interventions, such as focal therapy, offering a significant advancement in prostate cancer management. The study was authored by Sakina Mohammed Mota, Ph.D., and Alan Priester, Ph.D., and co-authored by Joshua Shubert, Jeremy Bong, James Sayre, Ph.D., Brittany Berry-Pusey, Ph.D., Wayne G. Brisbane, M.D., and Shyam Natarajan, Ph.D.

“This study is important because it shows the ability of AI to not only replicate expert physicians, but to go beyond human ability,” Brisbane said. “By increasing the accuracy of cancer identification in the prostate, more precise and effective treatment methods can be prescribed for patients.”

Unfold AI was just included in the American Medical Association’s (AMA) 2024 Current Procedural Terminology (CPT) code set. As a Category III code, Unfold AI will now be billable by insurance, improving access to this personalized prostate cancer care.

“It’s empowering for physicians to see this kind of innovation being validated through studies and recognized by the AMA,” Avenda Health CEO Dr. Shyam Natarajan stated. “

Avenda Health is creating a more personalized future of prostate cancer care. Using deep learning, Culver City-headquartered Avenda Health’s software maps a patient’s cancer in 3D, giving physicians precise information and the confidence to make care decisions.